Subscription (flat-rate)

cheapestinference

/cheapestinference · United States · est. 2025

Key facts

  • cheapestinference is a subscription (flat-rate) headquartered in United States, founded 2025.
  • Exposes an OpenAI-compatible API, so existing OpenAI SDK code can target it by changing the base URL.
  • Blended reference price is $0.30 per 1M tokens (in $0.25 / out $0.35).
  • Reference latency 340 ms TTFT at 120 tok/s throughput, with 99.5% reference uptime.
  • Editorial reputation index 83/100 from 96 weighted signals; 90-day trend improving.

Specification

Category
Subscription (flat-rate)
Headquarters
United States
Founded
2025
Model access
Open weights
Flagship / served
Flat-rate open-model access
Reference open model
Llama 3.3 70B
OpenAI-compatible API
Yes
Blended $/1M
$0.30 seed

Strengths & trade-offs

Strength

Flat-rate subscription pricing that decouples cost from token volume.

Trade-off

Newest entrant with the shortest public track record.


Profile reviewed 2026-07-10. Confidence for this listing:seed — Illustrative seed value pending first-party verification. NOT to be quoted as fact.Not affiliated with cheapestinference. ← Back to directory